帮助中心帮助中心

深度学习验证

训练稳健图像网络并验证图像网络稳健性

深度学习验证是一套评估深度神经网络属性的方法。例如，您可以验证网络的稳健性属性，计算网络输出边界，并找到对抗样本。

Deep Learning Toolbox™ Verification Library 支持包能够测试深度学习网络的稳健性属性。使用此库来验证深度学习网络针对对抗样本是否具有稳健性，计算针对一组输入边界的输出边界，并检测分布外数据。

使用 verifyNetworkRobustness 函数验证网络对对抗样本的稳健性。当在指定的输入下界和上界之间扰动输入时，如果网络的预测类不改变，则表明网络针对对抗输入具有稳健性。对于一组输入边界，该函数检查网络对于那些输入边界之间的对抗样本是否具有稳健性，并返回 verified、violated 或 unproven。
当输入介于指定的下界和上界之间时，使用 estimateNetworkOutputBounds 函数来估计网络返回的输出值的范围。使用此函数估计网络预测对输入扰动的敏感度。
使用 networkDistributionDiscriminator 函数创建一个分布判别器，该判别器将数据分为分布内和分布外。

函数

`estimateNetworkOutputBounds`	Estimate output bounds of deep learning network (自 R2022b 起)
`verifyNetworkRobustness`	Verify adversarial robustness of deep learning network (自 R2022b 起)
`networkDistributionDiscriminator`	Deep learning distribution discriminator (自 R2023a 起)
`isInNetworkDistribution`	Determine whether data is within the distribution of the network (自 R2023a 起)
`distributionScores`	Distribution confidence scores (自 R2023a 起)
`deep.gpu.deterministicAlgorithms`	Set determinism of deep learning operations on the GPU to get reproducible results (自 R2024b 起)

主题

Verify Robustness of Deep Learning Neural Network
This example shows how to verify the adversarial robustness of a deep learning neural network.
Deep Learning Visualization Methods
Learn about and compare deep learning visualization methods.

精选示例

Generate Untargeted and Targeted Adversarial Examples for Image Classification

Generate Untargeted and Targeted Adversarial Examples for Image Classification

Use the fast gradient sign method (FGSM) and the basic iterative method (BIM) to generate adversarial examples for a pretrained neural network.

打开实时脚本

Train Image Classification Network Robust to Adversarial Examples

Train Image Classification Network Robust to Adversarial Examples

Train a neural network that is robust to adversarial examples using fast gradient sign method (FGSM) adversarial training.

打开实时脚本

Train Robust Deep Learning Network with Jacobian Regularization

Train Robust Deep Learning Network with Jacobian Regularization

Train a neural network that is robust to adversarial examples using a Jacobian regularization scheme.

打开实时脚本

Generate Adversarial Examples for Semantic Segmentation

Generate Adversarial Examples for Semantic Segmentation

Generate adversarial examples for a semantic segmentation network using the basic iterative method (BIM).

打开实时脚本

Explore Semantic Segmentation Network Using Grad-CAM

Explore Semantic Segmentation Network Using Grad-CAM

Explore the predictions of a pretrained semantic segmentation network using Grad-CAM.

打开实时脚本